Ai/full autonomous flow (#359)

* Refactor bookkeeping error handling and introduce new error classes

- Introduced new error classes for better error categorization:
  - JournalEntryNotBalancedError
  - FiscalPeriodNotFoundError
  - EntryDateOutsideFiscalPeriodError
  - JournalEntryNotFoundError
  - CannotReverseNonPostedError
  - CannotCorrectNonPostedError
  - EntryAlreadyReversedError
  - CurrencyRevaluationAlreadyExistsError
  - InvalidMappingResultError
  - BookkeepingDatabaseError

- Updated existing functions in engine.ts and transaction-entries.ts to throw specific errors instead of generic ones.
- Enhanced error response handling in get-error-message.ts to provide localized messages for new error types.
- Added unit tests for new error classes and error handling functions to ensure correctness and coverage.

* feat(ai): implement AI proposal application and persistence

- Add apply.ts to handle the application of AI proposals, including match and booking steps.
- Introduce persist.ts for inserting and managing AI requests and proposals, ensuring unique constraints.
- Create re-validate.ts for validating proposals before acceptance, checking for stale conditions.
- Define database migrations for ai_requests and ai_proposals tables, including constraints and indexes.
- Enhance journal_entries with AI provenance tracking, linking entries to AI proposals.
- Update categorization_templates to distinguish AI-corrected templates.
- Add company settings for toggling AI flow and managing backfill processes.
- Extend processing_history to include AI-related events for better tracking.

* feat: add uncategorized transactions API and UI for transaction selection

- Implemented a new API endpoint for fetching uncategorized transactions with pagination and filtering options.
- Created ChangeTransactionDialog component for selecting alternative transactions based on AI proposals.
- Developed ReceiptDetailDialog to display detailed information about receipts, including upload functionality.
- Added TransactionDetailDialog for viewing transaction details with links to the transaction list.
- Introduced receipt quality assessment logic to evaluate extracted receipt data.
- Implemented feature flagging for the AI bookkeeping agent to control availability in different environments.

* feat: add manual receipt extraction dialog and integrate AWS Textract for expense analysis

- Added ManualExtractDialog component for user input when AI fails to extract receipt data.
- Implemented ReceiptsList component to manage and display uploaded receipts, including upload and rescan functionalities.
- Introduced Textract integration for analyzing expenses, extracting fields like total, vendor, and date.
- Updated package.json to include @aws-sdk/client-textract dependency.

* fix(ai): handle livsmedel VAT transition (12% → 6%) in booking prompt and re-validate guard

Add date-aware guidance to BOOKING_SYSTEM_PROMPT for the temporary livsmedel
VAT cut (Prop. 2025/26:55, 2026-04-01 to 2027-12-31), with restaurang/servering
carve-out at 12%. Add a re-validate safety net that rejects clearly-stale rate
labels for grocery-chain merchants relative to the entry date.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

lib/api/schemas.ts

@@ -394,6 +394,8 @@ export const UpdateSettingsSchema = z.object({
   invoice_show_plusgiro: z.boolean().optional(),
   invoice_late_fee_text: z.string().nullable().optional(),
   invoice_credit_terms_text: z.string().nullable().optional(),
+  // AI agent flow
+  ai_flow_enabled: z.boolean().optional(),
 }).refine(
   (data) => {
     // BFL 3 kap.: Enskild firma must have fiscal year starting January
@@ -768,3 +770,87 @@ export const CreateSalaryLineItemSchema = z.object({
 })
 
 export const UpdateSalaryLineItemSchema = CreateSalaryLineItemSchema.partial().omit({ salary_run_employee_id: true })
+
+// ============================================================
+// AI agent flow schemas
+// ============================================================
+
+const BookingProposalLineSchema = z.object({
+  account_number: accountNumber,
+  debit_amount: nonNegativeAmount,
+  credit_amount: nonNegativeAmount,
+  description: z.string().min(1).max(500),
+})
+
+const BookingProposalCounterpartyTemplateSchema = z.object({
+  counterparty_name: z.string().min(1).max(200),
+  debit_account: accountNumber,
+  credit_account: accountNumber,
+  vat_treatment: VatTreatmentSchema.nullable(),
+  category: TransactionCategorySchema.nullable(),
+})
+
+// Edit payload: the user's edited version of a booking proposal. Used in
+// the /accept endpoint when the user adjusted accounts/VAT before approving.
+export const EditBookingProposalSchema = z.object({
+  lines: z.array(BookingProposalLineSchema).min(2),
+  vat_treatment: VatTreatmentSchema.nullable(),
+  default_private: z.boolean(),
+  counterparty_template_proposal: BookingProposalCounterpartyTemplateSchema.nullable(),
+  fiscal_period_id: uuid,
+  entry_date: isoDate,
+  description: z.string().min(1).max(500),
+})
+
+// For match proposals, editing just means picking a different transaction.
+export const EditMatchProposalSchema = z.object({
+  matched_transaction_id: uuid,
+})
+
+export const AcceptProposalSchema = z.object({
+  version: z.number().int().nonnegative(),
+  edits: z.union([EditBookingProposalSchema, EditMatchProposalSchema]).optional(),
+})
+
+// Change the matched transaction on a pending match proposal without
+// accepting it. Source tells us whether the user picked one of the AI's
+// own alternatives, an AI-regenerated suggestion, or a manually-chosen
+// transaction — kept on edit_diff for learning signal.
+export const ChangeMatchProposalSchema = z.object({
+  version: z.number().int().nonnegative(),
+  matched_transaction_id: uuid,
+  source: z.enum(['user_alternative', 'user_manual', 'ai_regenerated']),
+})
+
+export const RejectProposalSchema = z.object({
+  version: z.number().int().nonnegative(),
+  reason: z.string().max(500).optional(),
+})
+
+export const BatchAcceptSchema = z.object({
+  proposal_ids: z.array(uuid).min(1).max(50),
+})
+
+export const ResolveRequestSchema = z.object({
+  response: z.record(z.string(), z.unknown()).optional(),
+})
+
+export const StartBackfillSchema = z.object({}).strict()
+
+export const RememberLearningSchema = z.object({
+  proposal_id: uuid,
+  counterparty_name: z.string().min(1).max(200),
+  debit_account: accountNumber,
+  credit_account: accountNumber,
+  vat_treatment: VatTreatmentSchema.nullable(),
+  category: TransactionCategorySchema.nullable(),
+})
+
+export const ListProposalsQuerySchema = z.object({
+  status: z
+    .enum(['pending', 'accepted', 'rejected', 'skipped', 'invalidated'])
+    .optional(),
+  step_type: z.enum(['match', 'booking']).optional(),
+  limit: z.coerce.number().int().min(1).max(100).default(20),
+  offset: z.coerce.number().int().min(0).default(0),
+})